Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 713 insertions, 0 deletions

diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
new file mode 100644
index 000000000..466c26df8
--- /dev/null
+++ b/net/sched/cls_bpf.c
@@ -0,0 +1,713 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Berkeley Packet Filter based traffic classifier
+ *
+ * Might be used to classify traffic through flexible, user-defined and
+ * possibly JIT-ed BPF filters for traffic control as an alternative to
+ * ematches.
+ *
+ * (C) 2013 Daniel Borkmann <dborkman@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+#include <linux/idr.h>
+
+#include <net/rtnetlink.h>
+#include <net/pkt_cls.h>
+#include <net/sock.h>
+#include <net/tc_wrapper.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
+MODULE_DESCRIPTION("TC BPF based classifier");
+
+#define CLS_BPF_NAME_LEN	256
+#define CLS_BPF_SUPPORTED_GEN_FLAGS		\
+	(TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW)
+
+struct cls_bpf_head {
+	struct list_head plist;
+	struct idr handle_idr;
+	struct rcu_head rcu;
+};
+
+struct cls_bpf_prog {
+	struct bpf_prog *filter;
+	struct list_head link;
+	struct tcf_result res;
+	bool exts_integrated;
+	u32 gen_flags;
+	unsigned int in_hw_count;
+	struct tcf_exts exts;
+	u32 handle;
+	u16 bpf_num_ops;
+	struct sock_filter *bpf_ops;
+	const char *bpf_name;
+	struct tcf_proto *tp;
+	struct rcu_work rwork;
+};
+
+static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
+	[TCA_BPF_CLASSID]	= { .type = NLA_U32 },
+	[TCA_BPF_FLAGS]		= { .type = NLA_U32 },
+	[TCA_BPF_FLAGS_GEN]	= { .type = NLA_U32 },
+	[TCA_BPF_FD]		= { .type = NLA_U32 },
+	[TCA_BPF_NAME]		= { .type = NLA_NUL_STRING,
+				    .len = CLS_BPF_NAME_LEN },
+	[TCA_BPF_OPS_LEN]	= { .type = NLA_U16 },
+	[TCA_BPF_OPS]		= { .type = NLA_BINARY,
+				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
+};
+
+static int cls_bpf_exec_opcode(int code)
+{
+	switch (code) {
+	case TC_ACT_OK:
+	case TC_ACT_SHOT:
+	case TC_ACT_STOLEN:
+	case TC_ACT_TRAP:
+	case TC_ACT_REDIRECT:
+	case TC_ACT_UNSPEC:
+		return code;
+	default:
+		return TC_ACT_UNSPEC;
+	}
+}
+
+TC_INDIRECT_SCOPE int cls_bpf_classify(struct sk_buff *skb,
+				       const struct tcf_proto *tp,
+				       struct tcf_result *res)
+{
+	struct cls_bpf_head *head = rcu_dereference_bh(tp->root);
+	bool at_ingress = skb_at_tc_ingress(skb);
+	struct cls_bpf_prog *prog;
+	int ret = -1;
+
+	list_for_each_entry_rcu(prog, &head->plist, link) {
+		int filter_res;
+
+		qdisc_skb_cb(skb)->tc_classid = prog->res.classid;
+
+		if (tc_skip_sw(prog->gen_flags)) {
+			filter_res = prog->exts_integrated ? TC_ACT_UNSPEC : 0;
+		} else if (at_ingress) {
+			/* It is safe to push/pull even if skb_shared() */
+			__skb_push(skb, skb->mac_len);
+			bpf_compute_data_pointers(skb);
+			filter_res = bpf_prog_run(prog->filter, skb);
+			__skb_pull(skb, skb->mac_len);
+		} else {
+			bpf_compute_data_pointers(skb);
+			filter_res = bpf_prog_run(prog->filter, skb);
+		}
+		if (unlikely(!skb->tstamp && skb->mono_delivery_time))
+			skb->mono_delivery_time = 0;
+
+		if (prog->exts_integrated) {
+			res->class   = 0;
+			res->classid = TC_H_MAJ(prog->res.classid) |
+				       qdisc_skb_cb(skb)->tc_classid;
+
+			ret = cls_bpf_exec_opcode(filter_res);
+			if (ret == TC_ACT_UNSPEC)
+				continue;
+			break;
+		}
+
+		if (filter_res == 0)
+			continue;
+		if (filter_res != -1) {
+			res->class   = 0;
+			res->classid = filter_res;
+		} else {
+			*res = prog->res;
+		}
+
+		ret = tcf_exts_exec(skb, &prog->exts, res);
+		if (ret < 0)
+			continue;
+
+		break;
+	}
+
+	return ret;
+}
+
+static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog)
+{
+	return !prog->bpf_ops;
+}
+
+static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
+			       struct cls_bpf_prog *oldprog,
+			       struct netlink_ext_ack *extack)
+{
+	struct tcf_block *block = tp->chain->block;
+	struct tc_cls_bpf_offload cls_bpf = {};
+	struct cls_bpf_prog *obj;
+	bool skip_sw;
+	int err;
+
+	skip_sw = prog && tc_skip_sw(prog->gen_flags);
+	obj = prog ?: oldprog;
+
+	tc_cls_common_offload_init(&cls_bpf.common, tp, obj->gen_flags, extack);
+	cls_bpf.command = TC_CLSBPF_OFFLOAD;
+	cls_bpf.exts = &obj->exts;
+	cls_bpf.prog = prog ? prog->filter : NULL;
+	cls_bpf.oldprog = oldprog ? oldprog->filter : NULL;
+	cls_bpf.name = obj->bpf_name;
+	cls_bpf.exts_integrated = obj->exts_integrated;
+
+	if (oldprog && prog)
+		err = tc_setup_cb_replace(block, tp, TC_SETUP_CLSBPF, &cls_bpf,
+					  skip_sw, &oldprog->gen_flags,
+					  &oldprog->in_hw_count,
+					  &prog->gen_flags, &prog->in_hw_count,
+					  true);
+	else if (prog)
+		err = tc_setup_cb_add(block, tp, TC_SETUP_CLSBPF, &cls_bpf,
+				      skip_sw, &prog->gen_flags,
+				      &prog->in_hw_count, true);
+	else
+		err = tc_setup_cb_destroy(block, tp, TC_SETUP_CLSBPF, &cls_bpf,
+					  skip_sw, &oldprog->gen_flags,
+					  &oldprog->in_hw_count, true);
+
+	if (prog && err) {
+		cls_bpf_offload_cmd(tp, oldprog, prog, extack);
+		return err;
+	}
+
+	if (prog && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW))
+		return -EINVAL;
+
+	return 0;
+}
+
+static u32 cls_bpf_flags(u32 flags)
+{
+	return flags & CLS_BPF_SUPPORTED_GEN_FLAGS;
+}
+
+static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
+			   struct cls_bpf_prog *oldprog,
+			   struct netlink_ext_ack *extack)
+{
+	if (prog && oldprog &&
+	    cls_bpf_flags(prog->gen_flags) !=
+	    cls_bpf_flags(oldprog->gen_flags))
+		return -EINVAL;
+
+	if (prog && tc_skip_hw(prog->gen_flags))
+		prog = NULL;
+	if (oldprog && tc_skip_hw(oldprog->gen_flags))
+		oldprog = NULL;
+	if (!prog && !oldprog)
+		return 0;
+
+	return cls_bpf_offload_cmd(tp, prog, oldprog, extack);
+}
+
+static void cls_bpf_stop_offload(struct tcf_proto *tp,
+				 struct cls_bpf_prog *prog,
+				 struct netlink_ext_ack *extack)
+{
+	int err;
+
+	err = cls_bpf_offload_cmd(tp, NULL, prog, extack);
+	if (err)
+		pr_err("Stopping hardware offload failed: %d\n", err);
+}
+
+static void cls_bpf_offload_update_stats(struct tcf_proto *tp,
+					 struct cls_bpf_prog *prog)
+{
+	struct tcf_block *block = tp->chain->block;
+	struct tc_cls_bpf_offload cls_bpf = {};
+
+	tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags, NULL);
+	cls_bpf.command = TC_CLSBPF_STATS;
+	cls_bpf.exts = &prog->exts;
+	cls_bpf.prog = prog->filter;
+	cls_bpf.name = prog->bpf_name;
+	cls_bpf.exts_integrated = prog->exts_integrated;
+
+	tc_setup_cb_call(block, TC_SETUP_CLSBPF, &cls_bpf, false, true);
+}
+
+static int cls_bpf_init(struct tcf_proto *tp)
+{
+	struct cls_bpf_head *head;
+
+	head = kzalloc(sizeof(*head), GFP_KERNEL);
+	if (head == NULL)
+		return -ENOBUFS;
+
+	INIT_LIST_HEAD_RCU(&head->plist);
+	idr_init(&head->handle_idr);
+	rcu_assign_pointer(tp->root, head);
+
+	return 0;
+}
+
+static void cls_bpf_free_parms(struct cls_bpf_prog *prog)
+{
+	if (cls_bpf_is_ebpf(prog))
+		bpf_prog_put(prog->filter);
+	else
+		bpf_prog_destroy(prog->filter);
+
+	kfree(prog->bpf_name);
+	kfree(prog->bpf_ops);
+}
+
+static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog)
+{
+	tcf_exts_destroy(&prog->exts);
+	tcf_exts_put_net(&prog->exts);
+
+	cls_bpf_free_parms(prog);
+	kfree(prog);
+}
+
+static void cls_bpf_delete_prog_work(struct work_struct *work)
+{
+	struct cls_bpf_prog *prog = container_of(to_rcu_work(work),
+						 struct cls_bpf_prog,
+						 rwork);
+	rtnl_lock();
+	__cls_bpf_delete_prog(prog);
+	rtnl_unlock();
+}
+
+static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog,
+			     struct netlink_ext_ack *extack)
+{
+	struct cls_bpf_head *head = rtnl_dereference(tp->root);
+
+	idr_remove(&head->handle_idr, prog->handle);
+	cls_bpf_stop_offload(tp, prog, extack);
+	list_del_rcu(&prog->link);
+	tcf_unbind_filter(tp, &prog->res);
+	if (tcf_exts_get_net(&prog->exts))
+		tcf_queue_work(&prog->rwork, cls_bpf_delete_prog_work);
+	else
+		__cls_bpf_delete_prog(prog);
+}
+
+static int cls_bpf_delete(struct tcf_proto *tp, void *arg, bool *last,
+			  bool rtnl_held, struct netlink_ext_ack *extack)
+{
+	struct cls_bpf_head *head = rtnl_dereference(tp->root);
+
+	__cls_bpf_delete(tp, arg, extack);
+	*last = list_empty(&head->plist);
+	return 0;
+}
+
+static void cls_bpf_destroy(struct tcf_proto *tp, bool rtnl_held,
+			    struct netlink_ext_ack *extack)
+{
+	struct cls_bpf_head *head = rtnl_dereference(tp->root);
+	struct cls_bpf_prog *prog, *tmp;
+
+	list_for_each_entry_safe(prog, tmp, &head->plist, link)
+		__cls_bpf_delete(tp, prog, extack);
+
+	idr_destroy(&head->handle_idr);
+	kfree_rcu(head, rcu);
+}
+
+static void *cls_bpf_get(struct tcf_proto *tp, u32 handle)
+{
+	struct cls_bpf_head *head = rtnl_dereference(tp->root);
+	struct cls_bpf_prog *prog;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		if (prog->handle == handle)
+			return prog;
+	}
+
+	return NULL;
+}
+
+static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog)
+{
+	struct sock_filter *bpf_ops;
+	struct sock_fprog_kern fprog_tmp;
+	struct bpf_prog *fp;
+	u16 bpf_size, bpf_num_ops;
+	int ret;
+
+	bpf_num_ops = nla_get_u16(tb[TCA_BPF_OPS_LEN]);
+	if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0)
+		return -EINVAL;
+
+	bpf_size = bpf_num_ops * sizeof(*bpf_ops);
+	if (bpf_size != nla_len(tb[TCA_BPF_OPS]))
+		return -EINVAL;
+
+	bpf_ops = kmemdup(nla_data(tb[TCA_BPF_OPS]), bpf_size, GFP_KERNEL);
+	if (bpf_ops == NULL)
+		return -ENOMEM;
+
+	fprog_tmp.len = bpf_num_ops;
+	fprog_tmp.filter = bpf_ops;
+
+	ret = bpf_prog_create(&fp, &fprog_tmp);
+	if (ret < 0) {
+		kfree(bpf_ops);
+		return ret;
+	}
+
+	prog->bpf_ops = bpf_ops;
+	prog->bpf_num_ops = bpf_num_ops;
+	prog->bpf_name = NULL;
+	prog->filter = fp;
+
+	return 0;
+}
+
+static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog,
+				 u32 gen_flags, const struct tcf_proto *tp)
+{
+	struct bpf_prog *fp;
+	char *name = NULL;
+	bool skip_sw;
+	u32 bpf_fd;
+
+	bpf_fd = nla_get_u32(tb[TCA_BPF_FD]);
+	skip_sw = gen_flags & TCA_CLS_FLAGS_SKIP_SW;
+
+	fp = bpf_prog_get_type_dev(bpf_fd, BPF_PROG_TYPE_SCHED_CLS, skip_sw);
+	if (IS_ERR(fp))
+		return PTR_ERR(fp);
+
+	if (tb[TCA_BPF_NAME]) {
+		name = nla_memdup(tb[TCA_BPF_NAME], GFP_KERNEL);
+		if (!name) {
+			bpf_prog_put(fp);
+			return -ENOMEM;
+		}
+	}
+
+	prog->bpf_ops = NULL;
+	prog->bpf_name = name;
+	prog->filter = fp;
+
+	if (fp->dst_needed)
+		tcf_block_netif_keep_dst(tp->chain->block);
+
+	return 0;
+}
+
+static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp,
+			     struct cls_bpf_prog *prog, unsigned long base,
+			     struct nlattr **tb, struct nlattr *est, u32 flags,
+			     struct netlink_ext_ack *extack)
+{
+	bool is_bpf, is_ebpf, have_exts = false;
+	u32 gen_flags = 0;
+	int ret;
+
+	is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS];
+	is_ebpf = tb[TCA_BPF_FD];
+	if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf))
+		return -EINVAL;
+
+	ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, flags,
+				extack);
+	if (ret < 0)
+		return ret;
+
+	if (tb[TCA_BPF_FLAGS]) {
+		u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]);
+
+		if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT)
+			return -EINVAL;
+
+		have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT;
+	}
+	if (tb[TCA_BPF_FLAGS_GEN]) {
+		gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]);
+		if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS ||
+		    !tc_flags_valid(gen_flags))
+			return -EINVAL;
+	}
+
+	prog->exts_integrated = have_exts;
+	prog->gen_flags = gen_flags;
+
+	ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) :
+		       cls_bpf_prog_from_efd(tb, prog, gen_flags, tp);
+	if (ret < 0)
+		return ret;
+
+	if (tb[TCA_BPF_CLASSID]) {
+		prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
+		tcf_bind_filter(tp, &prog->res, base);
+	}
+
+	return 0;
+}
+
+static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
+			  struct tcf_proto *tp, unsigned long base,
+			  u32 handle, struct nlattr **tca,
+			  void **arg, u32 flags,
+			  struct netlink_ext_ack *extack)
+{
+	struct cls_bpf_head *head = rtnl_dereference(tp->root);
+	struct cls_bpf_prog *oldprog = *arg;
+	struct nlattr *tb[TCA_BPF_MAX + 1];
+	struct cls_bpf_prog *prog;
+	int ret;
+
+	if (tca[TCA_OPTIONS] == NULL)
+		return -EINVAL;
+
+	ret = nla_parse_nested_deprecated(tb, TCA_BPF_MAX, tca[TCA_OPTIONS],
+					  bpf_policy, NULL);
+	if (ret < 0)
+		return ret;
+
+	prog = kzalloc(sizeof(*prog), GFP_KERNEL);
+	if (!prog)
+		return -ENOBUFS;
+
+	ret = tcf_exts_init(&prog->exts, net, TCA_BPF_ACT, TCA_BPF_POLICE);
+	if (ret < 0)
+		goto errout;
+
+	if (oldprog) {
+		if (handle && oldprog->handle != handle) {
+			ret = -EINVAL;
+			goto errout;
+		}
+	}
+
+	if (handle == 0) {
+		handle = 1;
+		ret = idr_alloc_u32(&head->handle_idr, prog, &handle,
+				    INT_MAX, GFP_KERNEL);
+	} else if (!oldprog) {
+		ret = idr_alloc_u32(&head->handle_idr, prog, &handle,
+				    handle, GFP_KERNEL);
+	}
+
+	if (ret)
+		goto errout;
+	prog->handle = handle;
+
+	ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], flags,
+				extack);
+	if (ret < 0)
+		goto errout_idr;
+
+	ret = cls_bpf_offload(tp, prog, oldprog, extack);
+	if (ret)
+		goto errout_parms;
+
+	if (!tc_in_hw(prog->gen_flags))
+		prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW;
+
+	if (oldprog) {
+		idr_replace(&head->handle_idr, prog, handle);
+		list_replace_rcu(&oldprog->link, &prog->link);
+		tcf_unbind_filter(tp, &oldprog->res);
+		tcf_exts_get_net(&oldprog->exts);
+		tcf_queue_work(&oldprog->rwork, cls_bpf_delete_prog_work);
+	} else {
+		list_add_rcu(&prog->link, &head->plist);
+	}
+
+	*arg = prog;
+	return 0;
+
+errout_parms:
+	cls_bpf_free_parms(prog);
+errout_idr:
+	if (!oldprog)
+		idr_remove(&head->handle_idr, prog->handle);
+errout:
+	tcf_exts_destroy(&prog->exts);
+	kfree(prog);
+	return ret;
+}
+
+static int cls_bpf_dump_bpf_info(const struct cls_bpf_prog *prog,
+				 struct sk_buff *skb)
+{
+	struct nlattr *nla;
+
+	if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_num_ops))
+		return -EMSGSIZE;
+
+	nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_num_ops *
+			  sizeof(struct sock_filter));
+	if (nla == NULL)
+		return -EMSGSIZE;
+
+	memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
+
+	return 0;
+}
+
+static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog,
+				  struct sk_buff *skb)
+{
+	struct nlattr *nla;
+
+	if (prog->bpf_name &&
+	    nla_put_string(skb, TCA_BPF_NAME, prog->bpf_name))
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, TCA_BPF_ID, prog->filter->aux->id))
+		return -EMSGSIZE;
+
+	nla = nla_reserve(skb, TCA_BPF_TAG, sizeof(prog->filter->tag));
+	if (nla == NULL)
+		return -EMSGSIZE;
+
+	memcpy(nla_data(nla), prog->filter->tag, nla_len(nla));
+
+	return 0;
+}
+
+static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, void *fh,
+			struct sk_buff *skb, struct tcmsg *tm, bool rtnl_held)
+{
+	struct cls_bpf_prog *prog = fh;
+	struct nlattr *nest;
+	u32 bpf_flags = 0;
+	int ret;
+
+	if (prog == NULL)
+		return skb->len;
+
+	tm->tcm_handle = prog->handle;
+
+	cls_bpf_offload_update_stats(tp, prog);
+
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	if (prog->res.classid &&
+	    nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid))
+		goto nla_put_failure;
+
+	if (cls_bpf_is_ebpf(prog))
+		ret = cls_bpf_dump_ebpf_info(prog, skb);
+	else
+		ret = cls_bpf_dump_bpf_info(prog, skb);
+	if (ret)
+		goto nla_put_failure;
+
+	if (tcf_exts_dump(skb, &prog->exts) < 0)
+		goto nla_put_failure;
+
+	if (prog->exts_integrated)
+		bpf_flags |= TCA_BPF_FLAG_ACT_DIRECT;
+	if (bpf_flags && nla_put_u32(skb, TCA_BPF_FLAGS, bpf_flags))
+		goto nla_put_failure;
+	if (prog->gen_flags &&
+	    nla_put_u32(skb, TCA_BPF_FLAGS_GEN, prog->gen_flags))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+
+	if (tcf_exts_dump_stats(skb, &prog->exts) < 0)
+		goto nla_put_failure;
+
+	return skb->len;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+}
+
+static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl,
+			       void *q, unsigned long base)
+{
+	struct cls_bpf_prog *prog = fh;
+
+	tc_cls_bind_class(classid, cl, q, &prog->res, base);
+}
+
+static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+			 bool rtnl_held)
+{
+	struct cls_bpf_head *head = rtnl_dereference(tp->root);
+	struct cls_bpf_prog *prog;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		if (!tc_cls_stats_dump(tp, arg, prog))
+			break;
+	}
+}
+
+static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
+			     void *cb_priv, struct netlink_ext_ack *extack)
+{
+	struct cls_bpf_head *head = rtnl_dereference(tp->root);
+	struct tcf_block *block = tp->chain->block;
+	struct tc_cls_bpf_offload cls_bpf = {};
+	struct cls_bpf_prog *prog;
+	int err;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		if (tc_skip_hw(prog->gen_flags))
+			continue;
+
+		tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags,
+					   extack);
+		cls_bpf.command = TC_CLSBPF_OFFLOAD;
+		cls_bpf.exts = &prog->exts;
+		cls_bpf.prog = add ? prog->filter : NULL;
+		cls_bpf.oldprog = add ? NULL : prog->filter;
+		cls_bpf.name = prog->bpf_name;
+		cls_bpf.exts_integrated = prog->exts_integrated;
+
+		err = tc_setup_cb_reoffload(block, tp, add, cb, TC_SETUP_CLSBPF,
+					    &cls_bpf, cb_priv, &prog->gen_flags,
+					    &prog->in_hw_count);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static struct tcf_proto_ops cls_bpf_ops __read_mostly = {
+	.kind		=	"bpf",
+	.owner		=	THIS_MODULE,
+	.classify	=	cls_bpf_classify,
+	.init		=	cls_bpf_init,
+	.destroy	=	cls_bpf_destroy,
+	.get		=	cls_bpf_get,
+	.change		=	cls_bpf_change,
+	.delete		=	cls_bpf_delete,
+	.walk		=	cls_bpf_walk,
+	.reoffload	=	cls_bpf_reoffload,
+	.dump		=	cls_bpf_dump,
+	.bind_class	=	cls_bpf_bind_class,
+};
+
+static int __init cls_bpf_init_mod(void)
+{
+	return register_tcf_proto_ops(&cls_bpf_ops);
+}
+
+static void __exit cls_bpf_exit_mod(void)
+{
+	unregister_tcf_proto_ops(&cls_bpf_ops);
+}
+
+module_init(cls_bpf_init_mod);
+module_exit(cls_bpf_exit_mod);